Compare commits
1 Commits
burn/378-1
...
burn/model
| Author | SHA1 | Date | |
|---|---|---|---|
|
f8f4678ee4 |
@@ -13,7 +13,6 @@ import concurrent.futures
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
@@ -41,44 +40,6 @@ from hermes_time import now as _hermes_now
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Minimum context tokens for cron jobs — models with smaller context are rejected
|
||||
# to prevent truncation of long prompts + tool outputs.
|
||||
CRON_MIN_CONTEXT_TOKENS = 64_000
|
||||
|
||||
|
||||
class ModelContextError(ValueError):
|
||||
"""Raised when a model's context length is too small for cron execution."""
|
||||
pass
|
||||
|
||||
|
||||
def _check_model_context_compat(model: str, base_url: str = None, config_context_length: int = None):
|
||||
"""Check if a model's context length meets the minimum for cron jobs.
|
||||
|
||||
Raises ModelContextError if the model's context is too small.
|
||||
Silently passes if detection fails (fail-open).
|
||||
"""
|
||||
if config_context_length is not None and config_context_length < CRON_MIN_CONTEXT_TOKENS:
|
||||
raise ModelContextError(
|
||||
f"Model '{model}' has {config_context_length:,} context tokens, "
|
||||
f"but cron jobs require at least {CRON_MIN_CONTEXT_TOKENS:,}. "
|
||||
f"Set a larger model in config.yaml or override per-job."
|
||||
)
|
||||
|
||||
try:
|
||||
from agent.model_metadata import get_model_context_length
|
||||
context_length = get_model_context_length(model, base_url=base_url)
|
||||
if context_length is not None and context_length < CRON_MIN_CONTEXT_TOKENS:
|
||||
raise ModelContextError(
|
||||
f"Model '{model}' has {context_length:,} context tokens, "
|
||||
f"but cron jobs require at least {CRON_MIN_CONTEXT_TOKENS:,}. "
|
||||
f"Set a larger model in config.yaml or override per-job."
|
||||
)
|
||||
except ModelContextError:
|
||||
raise
|
||||
except Exception:
|
||||
# Detection failure is non-fatal — fail open
|
||||
logger.debug("Context length detection failed for %s, skipping check", model)
|
||||
|
||||
|
||||
# =====================================================================
|
||||
# Deploy Sync Guard
|
||||
@@ -681,73 +642,6 @@ def _build_job_prompt(job: dict) -> str:
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
def _validate_local_service_access(job: dict, prompt: str) -> tuple[bool, str]:
|
||||
"""
|
||||
Validate that a cron job can access local services it references.
|
||||
|
||||
Detects prompts that reference localhost services (Ollama, etc.) and
|
||||
ensures the job is configured with a local base_url or provider.
|
||||
|
||||
Returns:
|
||||
(is_valid, warning_message) — True if no issue, False if mismatch detected.
|
||||
"""
|
||||
# Patterns that indicate local service access is required
|
||||
local_service_patterns = [
|
||||
r"localhost:\d+",
|
||||
r"127\.0\.0\.1:\d+",
|
||||
r"Check Ollama",
|
||||
r"check.*ollama",
|
||||
r"Ollama.*responding",
|
||||
r"ollama.*responding",
|
||||
r"local.*model.*health",
|
||||
r"health.*local.*model",
|
||||
r"ping.*localhost",
|
||||
r"curl.*localhost",
|
||||
]
|
||||
|
||||
# Check if prompt references local services
|
||||
prompt_lower = prompt.lower()
|
||||
references_local = any(
|
||||
re.search(pattern, prompt_lower) for pattern in local_service_patterns
|
||||
)
|
||||
|
||||
if not references_local:
|
||||
return True, ""
|
||||
|
||||
# Check if job is configured for local access
|
||||
base_url = job.get("base_url", "")
|
||||
provider = job.get("provider", "")
|
||||
model = job.get("model", "")
|
||||
|
||||
# Check for explicit local base_url
|
||||
if base_url and ("localhost" in base_url or "127.0.0.1" in base_url):
|
||||
return True, ""
|
||||
|
||||
# Check for Ollama provider
|
||||
if provider and "ollama" in provider.lower():
|
||||
return True, ""
|
||||
|
||||
# Check for common local model patterns in model name
|
||||
local_model_patterns = ["ollama", "llama", "mistral", "phi", "qwen", "gemma", "codellama"]
|
||||
if model and any(pattern in model.lower() for pattern in local_model_patterns):
|
||||
# Model name suggests local, but verify base_url
|
||||
if not base_url:
|
||||
return False, (
|
||||
f"Cron job '{job.get('name', job.get('id'))}' references local services "
|
||||
f"(localhost/Ollama) but has no base_url configured. "
|
||||
f"Set base_url='http://localhost:11434' for Ollama, or pin to a local provider."
|
||||
)
|
||||
return True, ""
|
||||
|
||||
# No local configuration detected
|
||||
return False, (
|
||||
f"Cron job '{job.get('name', job.get('id'))}' references local services "
|
||||
f"(localhost/Ollama) but is configured for cloud model "
|
||||
f"(model={model or 'default'}, provider={provider or 'default'}). "
|
||||
f"To check local Ollama, set base_url='http://localhost:11434' or provider='ollama'."
|
||||
)
|
||||
|
||||
|
||||
def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
"""
|
||||
Execute a single cron job.
|
||||
@@ -773,18 +667,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
|
||||
job_id = job["id"]
|
||||
job_name = job["name"]
|
||||
prompt = _build_job_prompt(job)
|
||||
|
||||
# Validate local service access — detect prompts referencing localhost/Ollama
|
||||
# that will fail on cloud models (#378)
|
||||
is_valid, warning = _validate_local_service_access(job, prompt)
|
||||
if not is_valid:
|
||||
logger.warning("Job '%s': %s", job_name, warning)
|
||||
# Inject warning into prompt so agent knows to report the issue
|
||||
prompt = (
|
||||
f"[SYSTEM WARNING: {warning}]\n\n"
|
||||
f"{prompt}"
|
||||
)
|
||||
|
||||
origin = _resolve_origin(job)
|
||||
_cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
|
||||
|
||||
|
||||
284
scripts/benchmark_local_models.py
Normal file
284
scripts/benchmark_local_models.py
Normal file
@@ -0,0 +1,284 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Benchmark local Ollama models against the 50 tok/s UX threshold.
|
||||
|
||||
Usage:
|
||||
python3 scripts/benchmark_local_models.py [--models MODEL1,MODEL2] [--prompt PROMPT] [--rounds N]
|
||||
python3 scripts/benchmark_local_models.py --all # test all pulled models
|
||||
python3 scripts/benchmark_local_models.py --json # JSON output for CI
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
import urllib.request
|
||||
import urllib.error
|
||||
from dataclasses import dataclass, asdict
|
||||
from typing import Optional
|
||||
|
||||
OLLAMA_BASE = os.environ.get("OLLAMA_BASE_URL", "http://localhost:11434")
|
||||
THRESHOLD_TOK_S = 50.0
|
||||
|
||||
BENCHMARK_PROMPT = (
|
||||
"Explain the difference between TCP and UDP protocols. "
|
||||
"Cover reliability, ordering, speed, and use cases. "
|
||||
"Be thorough but concise. Write at least 300 words."
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class BenchmarkResult:
|
||||
model: str
|
||||
size_gb: float
|
||||
prompt_tokens: int
|
||||
eval_tokens: int
|
||||
eval_duration_s: float
|
||||
tokens_per_second: float
|
||||
total_duration_s: float
|
||||
rounds: int
|
||||
avg_tok_s: float
|
||||
meets_threshold: bool
|
||||
error: Optional[str] = None
|
||||
|
||||
|
||||
def get_models() -> list[dict]:
|
||||
"""List all pulled Ollama models."""
|
||||
url = f"{OLLAMA_BASE}/api/tags"
|
||||
try:
|
||||
req = urllib.request.Request(url)
|
||||
with urllib.request.urlopen(req, timeout=10) as resp:
|
||||
data = json.loads(resp.read())
|
||||
return data.get("models", [])
|
||||
except Exception as e:
|
||||
print(f"Error connecting to Ollama at {OLLAMA_BASE}: {e}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def benchmark_model(model: str, prompt: str, num_predict: int = 512) -> dict:
|
||||
"""Run a single benchmark generation, return timing stats."""
|
||||
url = f"{OLLAMA_BASE}/api/generate"
|
||||
payload = json.dumps({
|
||||
"model": model,
|
||||
"prompt": prompt,
|
||||
"stream": False,
|
||||
"options": {
|
||||
"num_predict": num_predict,
|
||||
"temperature": 0.1, # low temp for consistent output
|
||||
},
|
||||
}).encode()
|
||||
|
||||
req = urllib.request.Request(url, data=payload, method="POST")
|
||||
req.add_header("Content-Type", "application/json")
|
||||
|
||||
start = time.monotonic()
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=300) as resp:
|
||||
data = json.loads(resp.read())
|
||||
except urllib.error.HTTPError as e:
|
||||
body = e.read().decode() if e.fp else str(e)
|
||||
raise RuntimeError(f"HTTP {e.code}: {body[:200]}")
|
||||
except Exception as e:
|
||||
raise RuntimeError(str(e))
|
||||
elapsed = time.monotonic() - start
|
||||
|
||||
prompt_tokens = data.get("prompt_eval_count", 0)
|
||||
eval_tokens = data.get("eval_count", 0)
|
||||
eval_duration_ns = data.get("eval_duration", 0)
|
||||
total_duration_ns = data.get("total_duration", 0)
|
||||
|
||||
eval_duration_s = eval_duration_ns / 1e9 if eval_duration_ns else elapsed
|
||||
total_duration_s = total_duration_ns / 1e9 if total_duration_ns else elapsed
|
||||
tok_s = eval_tokens / eval_duration_s if eval_duration_s > 0 else 0.0
|
||||
|
||||
return {
|
||||
"prompt_tokens": prompt_tokens,
|
||||
"eval_tokens": eval_tokens,
|
||||
"eval_duration_s": round(eval_duration_s, 2),
|
||||
"total_duration_s": round(total_duration_s, 2),
|
||||
"tokens_per_second": round(tok_s, 1),
|
||||
}
|
||||
|
||||
|
||||
def run_benchmark(
|
||||
model_name: str,
|
||||
model_size: float,
|
||||
prompt: str,
|
||||
rounds: int,
|
||||
num_predict: int,
|
||||
threshold: float = 50.0,
|
||||
) -> BenchmarkResult:
|
||||
"""Run multiple rounds and compute average."""
|
||||
results = []
|
||||
errors = []
|
||||
|
||||
for i in range(rounds):
|
||||
try:
|
||||
r = benchmark_model(model_name, prompt, num_predict)
|
||||
results.append(r)
|
||||
print(f" Round {i+1}/{rounds}: {r['tokens_per_second']} tok/s "
|
||||
f"({r['eval_tokens']} tokens in {r['eval_duration_s']}s)")
|
||||
except Exception as e:
|
||||
errors.append(str(e))
|
||||
print(f" Round {i+1}/{rounds}: ERROR - {e}")
|
||||
|
||||
if not results:
|
||||
return BenchmarkResult(
|
||||
model=model_name,
|
||||
size_gb=model_size,
|
||||
prompt_tokens=0, eval_tokens=0,
|
||||
eval_duration_s=0, tokens_per_second=0,
|
||||
total_duration_s=0, rounds=rounds,
|
||||
avg_tok_s=0, meets_threshold=False,
|
||||
error="; ".join(errors),
|
||||
)
|
||||
|
||||
avg_tok_s = sum(r["tokens_per_second"] for r in results) / len(results)
|
||||
avg_tok_s = round(avg_tok_s, 1)
|
||||
|
||||
return BenchmarkResult(
|
||||
model=model_name,
|
||||
size_gb=model_size,
|
||||
prompt_tokens=sum(r["prompt_tokens"] for r in results) // len(results),
|
||||
eval_tokens=sum(r["eval_tokens"] for r in results) // len(results),
|
||||
eval_duration_s=round(sum(r["eval_duration_s"] for r in results) / len(results), 2),
|
||||
tokens_per_second=avg_tok_s,
|
||||
total_duration_s=round(sum(r["total_duration_s"] for r in results) / len(results), 2),
|
||||
rounds=len(results),
|
||||
avg_tok_s=avg_tok_s,
|
||||
meets_threshold=avg_tok_s >= threshold,
|
||||
)
|
||||
|
||||
|
||||
def format_report(results: list[BenchmarkResult], threshold: float = 50.0) -> str:
|
||||
"""Format a human-readable benchmark report."""
|
||||
lines = []
|
||||
lines.append("")
|
||||
lines.append("=" * 72)
|
||||
lines.append(f" LOCAL MODEL BENCHMARK — {threshold:.0f} tok/s UX Threshold")
|
||||
lines.append("=" * 72)
|
||||
lines.append("")
|
||||
|
||||
# Summary table
|
||||
header = f"{'Model':<25} {'Size':>6} {'tok/s':>8} {'Threshold':>10} {'Status':>8}"
|
||||
lines.append(header)
|
||||
lines.append("-" * 72)
|
||||
|
||||
passed = 0
|
||||
failed = 0
|
||||
errors = 0
|
||||
|
||||
for r in sorted(results, key=lambda x: x.avg_tok_s, reverse=True):
|
||||
size_str = f"{r.size_gb:.1f}GB"
|
||||
tok_s_str = f"{r.avg_tok_s:.1f}"
|
||||
|
||||
if r.error:
|
||||
status = "ERROR"
|
||||
errors += 1
|
||||
elif r.meets_threshold:
|
||||
status = "PASS"
|
||||
passed += 1
|
||||
else:
|
||||
status = "FAIL"
|
||||
failed += 1
|
||||
|
||||
marker = ">" if r.meets_threshold else "X" if r.error else "!"
|
||||
thresh_str = f">= {threshold:.0f}"
|
||||
lines.append(f" {marker} {r.model:<23} {size_str:>6} {tok_s_str:>8} {thresh_str:>10} {status:>8}")
|
||||
|
||||
lines.append("-" * 72)
|
||||
lines.append(f" Passed: {passed} | Failed: {failed} | Errors: {errors} | Total: {len(results)}")
|
||||
lines.append("")
|
||||
|
||||
# Detail section for failures
|
||||
failures = [r for r in results if not r.meets_threshold and not r.error]
|
||||
if failures:
|
||||
lines.append(" FAILED MODELS (below threshold):")
|
||||
for r in sorted(failures, key=lambda x: x.avg_tok_s):
|
||||
gap = threshold - r.avg_tok_s
|
||||
lines.append(f" - {r.model}: {r.avg_tok_s:.1f} tok/s "
|
||||
f"({gap:.1f} tok/s short, {r.eval_tokens} avg tokens/round)")
|
||||
lines.append("")
|
||||
|
||||
error_list = [r for r in results if r.error]
|
||||
if error_list:
|
||||
lines.append(" ERRORS:")
|
||||
for r in error_list:
|
||||
lines.append(f" - {r.model}: {r.error}")
|
||||
lines.append("")
|
||||
|
||||
# Hardware info
|
||||
import platform
|
||||
lines.append(f" Host: {platform.node()} | {platform.system()} {platform.release()}")
|
||||
lines.append(f" Ollama: {OLLAMA_BASE}")
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Benchmark local Ollama models vs 50 tok/s threshold")
|
||||
parser.add_argument("--models", help="Comma-separated model names (default: all)")
|
||||
parser.add_argument("--prompt", default=BENCHMARK_PROMPT, help="Benchmark prompt")
|
||||
parser.add_argument("--rounds", type=int, default=3, help="Rounds per model (default: 3)")
|
||||
parser.add_argument("--tokens", type=int, default=512, help="Max tokens to generate (default: 512)")
|
||||
parser.add_argument("--json", action="store_true", help="JSON output for CI")
|
||||
parser.add_argument("--all", action="store_true", help="Test all pulled models")
|
||||
parser.add_argument("--threshold", type=float, default=THRESHOLD_TOK_S, help="tok/s threshold")
|
||||
args = parser.parse_args()
|
||||
threshold = args.threshold
|
||||
|
||||
# Get model list
|
||||
available = get_models()
|
||||
if not available:
|
||||
print("No models found. Pull a model first: ollama pull <model>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if args.models:
|
||||
names = [m.strip() for m in args.models.split(",")]
|
||||
models = [m for m in available if m["name"] in names]
|
||||
missing = set(names) - set(m["name"] for m in models)
|
||||
if missing:
|
||||
print(f"Models not found: {', '.join(missing)}", file=sys.stderr)
|
||||
print(f"Available: {', '.join(m['name'] for m in available)}", file=sys.stderr)
|
||||
else:
|
||||
models = available
|
||||
|
||||
print(f"Benchmarking {len(models)} model(s) against {threshold} tok/s threshold")
|
||||
print(f"Ollama: {OLLAMA_BASE} | Rounds: {args.rounds} | Max tokens: {args.tokens}")
|
||||
print()
|
||||
|
||||
results = []
|
||||
for m in models:
|
||||
name = m["name"]
|
||||
size_gb = m.get("size", 0) / (1024**3)
|
||||
print(f" {name} ({size_gb:.1f}GB):")
|
||||
|
||||
result = run_benchmark(name, size_gb, args.prompt, args.rounds, args.tokens, threshold)
|
||||
results.append(result)
|
||||
|
||||
# Output
|
||||
report = format_report(results, threshold)
|
||||
if args.json:
|
||||
output = {
|
||||
"threshold_tok_s": threshold,
|
||||
"ollama_base": OLLAMA_BASE,
|
||||
"rounds": args.rounds,
|
||||
"results": [asdict(r) for r in results],
|
||||
"passed": sum(1 for r in results if r.meets_threshold),
|
||||
"failed": sum(1 for r in results if not r.meets_threshold and not r.error),
|
||||
"errors": sum(1 for r in results if r.error),
|
||||
}
|
||||
print(json.dumps(output, indent=2))
|
||||
else:
|
||||
print(report)
|
||||
|
||||
# Exit code: 0 if all pass, 1 if any fail/error
|
||||
if any(not r.meets_threshold or r.error for r in results):
|
||||
sys.exit(1)
|
||||
sys.exit(0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -7,7 +7,7 @@ from unittest.mock import AsyncMock, patch, MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from cron.scheduler import _resolve_origin, _resolve_delivery_target, _deliver_result, run_job, SILENT_MARKER, _build_job_prompt, _check_model_context_compat, ModelContextError, CRON_MIN_CONTEXT_TOKENS, _validate_local_service_access
|
||||
from cron.scheduler import _resolve_origin, _resolve_delivery_target, _deliver_result, run_job, SILENT_MARKER, _build_job_prompt, _check_model_context_compat, ModelContextError, CRON_MIN_CONTEXT_TOKENS
|
||||
|
||||
|
||||
class TestResolveOrigin:
|
||||
@@ -1001,99 +1001,3 @@ class TestCheckModelContextCompat:
|
||||
):
|
||||
with pytest.raises(ModelContextError):
|
||||
_check_model_context_compat("borderline-model")
|
||||
|
||||
|
||||
class TestValidateLocalServiceAccess:
|
||||
"""Tests for _validate_local_service_access — detects local service mismatches (#378)."""
|
||||
|
||||
def test_no_local_reference_passes(self):
|
||||
"""Prompt without local references always passes."""
|
||||
job = {"name": "test", "model": "gpt-4"}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check system health")
|
||||
assert is_valid is True
|
||||
assert msg == ""
|
||||
|
||||
def test_localhost_reference_with_local_base_url(self):
|
||||
"""Prompt references localhost but job has local base_url — passes."""
|
||||
job = {
|
||||
"name": "health-check",
|
||||
"model": "llama3",
|
||||
"base_url": "http://localhost:11434/v1",
|
||||
}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check if Ollama is responding on localhost:11434")
|
||||
assert is_valid is True
|
||||
assert msg == ""
|
||||
|
||||
def test_localhost_reference_with_cloud_model_fails(self):
|
||||
"""Prompt references localhost but job uses cloud model — fails."""
|
||||
job = {
|
||||
"name": "health-check",
|
||||
"model": "nous/mimo-v2-pro",
|
||||
"provider": "nous",
|
||||
}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check Ollama is responding on localhost:11434")
|
||||
assert is_valid is False
|
||||
assert "localhost" in msg.lower() or "ollama" in msg.lower()
|
||||
assert "cloud model" in msg.lower() or "base_url" in msg.lower()
|
||||
|
||||
def test_ollama_check_with_ollama_provider(self):
|
||||
"""Prompt references Ollama and job uses ollama provider — passes."""
|
||||
job = {
|
||||
"name": "ollama-health",
|
||||
"provider": "ollama",
|
||||
"base_url": "http://localhost:11434",
|
||||
}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check Ollama is responding")
|
||||
assert is_valid is True
|
||||
assert msg == ""
|
||||
|
||||
def test_case_insensitive_detection(self):
|
||||
"""Detection is case-insensitive."""
|
||||
job = {"name": "test", "model": "gpt-4"}
|
||||
# Lowercase
|
||||
is_valid, _ = _validate_local_service_access(job, "check ollama is responding")
|
||||
assert is_valid is False
|
||||
# Uppercase
|
||||
is_valid, _ = _validate_local_service_access(job, "CHECK OLLAMA IS RESPONDING")
|
||||
assert is_valid is False
|
||||
# Mixed case
|
||||
is_valid, _ = _validate_local_service_access(job, "Check if Ollama Is Responding")
|
||||
assert is_valid is False
|
||||
|
||||
def test_curl_localhost_detected(self):
|
||||
"""curl localhost references are detected."""
|
||||
job = {"name": "test", "model": "gpt-4"}
|
||||
is_valid, _ = _validate_local_service_access(job, "Run curl localhost:8080/health")
|
||||
assert is_valid is False
|
||||
|
||||
def test_127_0_0_1_detected(self):
|
||||
"""127.0.0.1 references are detected."""
|
||||
job = {"name": "test", "model": "gpt-4"}
|
||||
is_valid, _ = _validate_local_service_access(job, "Check http://127.0.0.1:11434/api/tags")
|
||||
assert is_valid is False
|
||||
|
||||
def test_local_model_name_without_base_url_fails(self):
|
||||
"""Model name suggests local but no base_url — fails."""
|
||||
job = {"name": "test", "model": "llama3"}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check Ollama is responding")
|
||||
assert is_valid is False
|
||||
assert "base_url" in msg
|
||||
|
||||
def test_local_model_name_with_base_url_passes(self):
|
||||
"""Model name suggests local and has base_url — passes."""
|
||||
job = {"name": "test", "model": "llama3", "base_url": "http://localhost:11434"}
|
||||
is_valid, msg = _validate_local_service_access(job, "Check Ollama is responding")
|
||||
assert is_valid is True
|
||||
assert msg == ""
|
||||
|
||||
def test_nightwatch_health_monitor_scenario(self):
|
||||
"""Reproduces the exact #378 scenario."""
|
||||
job = {
|
||||
"name": "nightwatch-health-monitor",
|
||||
"model": "nous/mimo-v2-pro",
|
||||
"provider": "nous",
|
||||
}
|
||||
prompt = "Check Ollama is responding. Run curl http://localhost:11434/api/tags and report status."
|
||||
is_valid, msg = _validate_local_service_access(job, prompt)
|
||||
assert is_valid is False
|
||||
assert "nightwatch-health-monitor" in msg or "localhost" in msg
|
||||
|
||||
Reference in New Issue
Block a user